Significance of Data Augmentation for Improving Cleft Lip and Palate Speech Recognition
This work addresses the problem of limited domain-specific data for pathological speech recognition, particularly for children with articulatory impairments, but it is incremental as it applies existing augmentation methods to a new dataset.
The study tackled the challenge of recognizing pathological speech from children with cleft lip and palate by investigating data augmentation techniques, resulting in improved phone error rates, with CycleGAN, VTLP, and reverberation methods showing the most significant gains.
The automatic recognition of pathological speech, particularly from children with any articulatory impairment, is a challenging task due to various reasons. The lack of available domain specific data is one such obstacle that hinders its usage for different speech-based applications targeting pathological speakers. In line with the challenge, in this work, we investigate a few data augmentation techniques to simulate training data for improving the children speech recognition considering the case of cleft lip and palate (CLP) speech. The augmentation techniques explored in this study, include vocal tract length perturbation (VTLP), reverberation, speaking rate, pitch modification, and speech feature modification using cycle consistent adversarial networks (CycleGAN). Our study finds that the data augmentation methods significantly improve the CLP speech recognition performance, which is more evident when we used feature modification using CycleGAN, VTLP and reverberation based methods. More specifically, the results from this study show that our systems produce an improved phone error rate compared to the systems without data augmentation.